Unverified50% confidenceFactExact time
ResNet-50 and MobileNetV3 are both commonly used ImageNet-pretrained backbone networks; the former has high accuracy, while the latter is suited to edge deployment.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMobileNetV3 是 Google 针对移动端和边缘设备设计的轻量级架构，采用深度可分离卷积将计算量降低约 8-9 倍，Large 版本在 ImageNet 上达到 75.2% Top-1 精度，推理延迟约为 ResNet-50 的 1/570% similarUnverifiedIn 2015, He Kaiming et al. proposed ResNet, which introduced skip connections (residual connections), making it possible to train networks of hundreds or even thousands of layers.67% similarUnverifiedMoveNet adopts a CenterNet-style single-stage detection architecture paired with a MobileNetV2 backbone network, compressing inference latency to under 10 ms.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1094223API
curl https://kongchang.com/api/v1/knowledge/claims/1094223MCP
get_claim(id=1094223)